Self-Supervised Learning

This is a subset of unsupervised learning where we try to minimize our loss by trying replicate our output data to our input data.

Lilian Weng

Two methods:

  1. Self-Prediction: Given an individual data sample, the task is to predict one part of the sample given the other part. Ex
    1. crop part of an image and train a model to predict the pixels cropped, or
    2. decolourize our original image, and predict a colourized image
  2. Contrastive Learning: Given multiple data samples, the task is to predict the relationship among them. Ex:
    1. Embeddings?

hg hytfr dgtyfr tgyfrdtgyhgt frgyh